> ## Documentation Index > Fetch the complete documentation index at: https://docs.ringg.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create Agent > Creates a new AI agent with the specified configuration. The agent will be created with a single prompt-based flow. Create a new assistant programmatically. This endpoint is best for productized setup flows where your application creates Ringg assistants from templates or customer-provided configuration. ## When to use * Onboard customers into a pre-defined assistant template. * Create one assistant per team, location, or campaign type. * Provision assistants from your own admin backend. ## Integration notes * For most teams, creating the assistant in the dashboard first is simpler. * Store the returned `agent_id`; it is required for calls and campaigns. * Keep prompts concise and make every variable explicit in `custom_args_values` or campaign CSV mappings. ## After creation Use [get assistants](/api-reference/endpoint/assistant/get-assistants) to confirm the assistant is visible, then test with one [individual call](/api-reference/endpoint/calling/initiate-individual-call) before using campaigns. ## OpenAPI ````yaml post /public/agent openapi: 3.0.0 info: title: Ringg AI API Documentation description: >- This is the documentation for the Ringg AI APIs. The Ringg AI API follows RESTful principles, making it intuitive and easy to integrate with your applications. All API requests should be made to the base URL. The API accepts and returns data in JSON format. Ensure your requests include the appropriate Content-Type header for POST and PATCH requests. version: 2.0.0 servers: - url: https://prod-api.ringg.ai/ca/api/v0 security: [] tags: - name: workspace description: Endpoints for managing your workspace. - name: agent description: Endpoints for managing assistants (agents). - name: calling description: Endpoints for making and managing calls. - name: campaign description: Endpoints for managing campaigns. - name: analytics description: Endpoints for accessing call analytics and performance metrics. - name: termination description: Endpoints for terminating active calls using different methods. - name: knowledgebase description: Endpoints for managing knowledge bases. paths: /public/agent: post: tags: - agent summary: Create Agent description: >- Creates a new AI agent with the specified configuration. The agent will be created with a single prompt-based flow. operationId: createAgent parameters: - name: X-API-KEY in: header description: (Required) Your Ringg AI API key. required: true schema: type: string example: 7251cb4b-3373-43a4-844c-b27a1d45e0c9 requestBody: required: true content: application/json: schema: type: object required: - agent_name - introduction_and_objective - response_guidelines - task - primary_language - voice_id - intro_message properties: agent_name: type: string maxLength: 100 description: (Required) Name of the agent example: My Sales Agent introduction_and_objective: type: string maxLength: 2000 description: (Required) Introduction and objective of the agent example: You are a customer support agent for Acme Corp. response_guidelines: type: string maxLength: 3000 description: (Required) Guidelines for how the agent should respond example: >- Be polite, helpful, and concise. Always confirm understanding. task: type: string maxLength: 1500 description: (Required) The task the agent should perform example: >- Help customers with their orders and answer product questions. faq: type: string maxLength: 5000 description: (Optional) FAQ content for the agent example: 'Q: What are your hours? A: We are open 9am-6pm IST.' sample_conversations: type: string maxLength: 5000 description: >- (Optional) Example conversations for the agent. Use \n for newlines between turns. example: |- User: Hi Agent: Hello! How can I help you today? primary_language: type: string enum: - en-US - en-IN - hi-IN - ta-IN - te-IN - bn-IN - mr-IN - kn-IN - ka-IN description: (Required) Primary language locale for the agent example: en-IN secondary_language: type: string enum: - en-US - en-IN - hi-IN - ta-IN - te-IN - bn-IN - mr-IN - kn-IN - ka-IN description: (Optional) Secondary language locale for the agent example: hi-IN voice_id: type: string format: uuid description: >- (Required) Internal AgentVoice ID (UUID). Get available voices from the Get Assistant Voices endpoint. example: 02ad256b-092b-4048-bea0-5af46a452b98 intro_message: type: string maxLength: 500 description: >- (Required) Introduction message the agent will speak when the call starts example: >- Hello, this is Sarah from Acme Corp. How can I assist you today? agent_type: type: string enum: - inbound - outbound - outbound_inbound default: outbound description: (Required) Type of agent. Defaults to outbound. example: outbound custom_variables: type: array items: type: string description: >- (Optional) Custom variables for the agent. For outbound agents, callee_name and mobile_number are always included automatically. example: - callee_name - mobile_number - company - lead_source responses: '200': description: Agent created successfully. content: application/json: schema: type: object properties: success: type: boolean example: true data: type: object properties: id: type: string description: The unique ID of the created agent example: edd618d3-f473-4ac1-b5fa-f1a3981666ff version: type: string description: The version slug of the agent example: v1 created_at: type: string format: date-time example: '2024-12-16T13:03:29.947147+00:00' message: type: string example: Agent created successfully '400': description: >- Bad Request - Invalid parameters or voice does not support the selected language. content: application/json: schema: type: object properties: success: type: boolean example: false error: type: object properties: code: type: string example: VOICE_LANGUAGE_MISMATCH message: type: string example: Voice does not support language 'en-US' '401': description: Unauthorized - Invalid or missing API key. ````